{ "fullyEncodeReservedExpansion": true, "version_module": true, "documentationLink": "https://cloud.google.com/video-intelligence/docs/", "name": "videointelligence", "canonicalName": "Cloud Video Intelligence", "version": "v1p3beta1", "protocol": "rest", "parameters": { "upload_protocol": { "type": "string", "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").", "location": "query" }, "oauth_token": { "type": "string", "description": "OAuth 2.0 token for the current user.", "location": "query" }, "access_token": { "type": "string", "description": "OAuth access token.", "location": "query" }, "key": { "type": "string", "description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.", "location": "query" }, "quotaUser": { "type": "string", "description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.", "location": "query" }, "uploadType": { "type": "string", "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").", "location": "query" }, "fields": { "description": "Selector specifying which fields to include in a partial response.", "location": "query", "type": "string" }, "alt": { "default": "json", "enumDescriptions": [ "Responses with Content-Type of application/json", "Media download with context-dependent Content-Type", "Responses with Content-Type of application/x-protobuf" ], "type": "string", "enum": [ "json", "media", "proto" ], "description": "Data format for response.", "location": "query" }, "prettyPrint": { "type": "boolean", "description": "Returns response with indentations and line breaks.", "location": "query", "default": "true" }, "$.xgafv": { "type": "string", "enum": [ "1", "2" ], "enumDescriptions": [ "v1 error format", "v2 error format" ], "description": "V1 error format.", "location": "query" }, "callback": { "type": "string", "description": "JSONP", "location": "query" } }, "resources": { "videos": { "methods": { "annotate": { "response": { "$ref": "GoogleLongrunning_Operation" }, "request": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoRequest" }, "path": "v1p3beta1/videos:annotate", "httpMethod": "POST", "parameterOrder": [], "flatPath": "v1p3beta1/videos:annotate", "description": "Performs asynchronous video annotation. Progress and results can be retrieved through the `google.longrunning.Operations` interface. `Operation.metadata` contains `AnnotateVideoProgress` (progress). `Operation.response` contains `AnnotateVideoResponse` (results).", "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "id": "videointelligence.videos.annotate", "parameters": {} } } } }, "batchPath": "batch", "rootUrl": "https://videointelligence.googleapis.com/", "ownerDomain": "google.com", "schemas": { "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute": { "properties": { "name": { "type": "string", "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document." }, "value": { "type": "string", "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc." }, "confidence": { "type": "number", "format": "float", "description": "Detected attribute confidence. Range [0, 1]." } }, "id": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute", "type": "object", "description": "A generic detected attribute represented by name in string format." }, "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation": { "id": "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation", "type": "object", "properties": { "segments": { "type": "array", "description": "All video segments where a face was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceSegment" } }, "frames": { "description": "All video frames where a face was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceFrame" }, "type": "array" }, "thumbnail": { "description": "Thumbnail of a representative face view (in JPEG format).", "type": "string", "format": "byte" } }, "description": "Deprecated. No effect.", "deprecated": true }, "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox": { "id": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox", "type": "object", "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", "properties": { "bottom": { "description": "Bottom Y coordinate.", "type": "number", "format": "float" }, "left": { "description": "Left X coordinate.", "type": "number", "format": "float" }, "top": { "type": "number", "format": "float", "description": "Top Y coordinate." }, "right": { "type": "number", "format": "float", "description": "Right X coordinate." } } }, "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly": { "properties": { "vertices": { "description": "Normalized vertices of the bounding polygon.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex" }, "type": "array" } }, "id": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly", "type": "object", "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box." }, "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark": { "description": "A generic detected landmark represented by name in string format and a 2D location.", "id": "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark", "type": "object", "properties": { "point": { "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex" }, "confidence": { "description": "The confidence score of the detected landmark. Range [0, 1].", "type": "number", "format": "float" }, "name": { "description": "The name of this landmark, for example, left_hand, right_shoulder.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingConfig": { "properties": { "model": { "type": "string", "description": "Model to use for object tracking. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\"." } }, "description": "Config for OBJECT_TRACKING.", "id": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingConfig", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute": { "description": "A generic detected attribute represented by name in string format.", "id": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute", "type": "object", "properties": { "confidence": { "description": "Detected attribute confidence. Range [0, 1].", "type": "number", "format": "float" }, "value": { "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.", "type": "string" }, "name": { "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", "type": "string" } } }, "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress": { "properties": { "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "progressPercent": { "type": "integer", "format": "int32", "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed." }, "updateTime": { "type": "string", "format": "google-datetime", "description": "Time of the most recent update." }, "segment": { "description": "Specifies which segment is being tracked if the request contains more than one segment.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "startTime": { "type": "string", "format": "google-datetime", "description": "Time when the request was received." }, "feature": { "description": "Specifies which feature is being tracked if the request contains more than one feature.", "type": "string", "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "PERSON_DETECTION" ], "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Person detection." ] }, "exportStatus": { "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request.", "$ref": "GoogleCloudVideointelligenceV1beta2_ExportToOutputUriStatus" } }, "description": "Annotation progress for a single video.", "id": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress", "type": "object" }, "GoogleCloudVideointelligenceV1_WordInfo": { "properties": { "speakerLabel": { "readOnly": true, "type": "string", "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word." }, "speakerTag": { "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "type": "integer", "format": "int32", "readOnly": true }, "startTime": { "type": "string", "format": "google-duration", "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary." }, "word": { "type": "string", "description": "The word corresponding to this set of information." }, "endTime": { "type": "string", "format": "google-duration", "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary." }, "confidence": { "type": "number", "format": "float", "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true } }, "id": "GoogleCloudVideointelligenceV1_WordInfo", "type": "object", "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`." }, "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame": { "properties": { "timeOffset": { "description": "The timestamp of the frame in microseconds.", "type": "string", "format": "google-duration" }, "normalizedBoundingBox": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox", "description": "The normalized bounding box location of this object track for the frame." } }, "id": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame", "type": "object", "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence." }, "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoProgress": { "id": "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoProgress", "type": "object", "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "properties": { "annotationProgress": { "type": "array", "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress" } } } }, "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionConfig": { "description": "Config for PERSON_DETECTION.", "id": "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionConfig", "type": "object", "properties": { "includePoseLandmarks": { "type": "boolean", "description": "Whether to enable pose landmarks detection. Ignored if 'include_bounding_boxes' is set to false." }, "includeAttributes": { "type": "boolean", "description": "Whether to enable person attributes detection, such as cloth color (black, blue, etc), type (coat, dress, etc), pattern (plain, floral, etc), hair, etc. Ignored if 'include_bounding_boxes' is set to false." }, "includeBoundingBoxes": { "type": "boolean", "description": "Whether bounding boxes are included in the person detection annotation output." } } }, "GoogleCloudVideointelligenceV1_LabelAnnotation": { "properties": { "entity": { "$ref": "GoogleCloudVideointelligenceV1_Entity", "description": "Detected entity." }, "frames": { "type": "array", "description": "All video frames where a label was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelFrame" } }, "categoryEntities": { "type": "array", "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", "items": { "$ref": "GoogleCloudVideointelligenceV1_Entity" } }, "version": { "description": "Feature version.", "type": "string" }, "segments": { "type": "array", "description": "All video segments where a label was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelSegment" } } }, "description": "Label annotation.", "id": "GoogleCloudVideointelligenceV1_LabelAnnotation", "type": "object" }, "GoogleCloudVideointelligenceV1_DetectedLandmark": { "properties": { "name": { "description": "The name of this landmark, for example, left_hand, right_shoulder.", "type": "string" }, "point": { "$ref": "GoogleCloudVideointelligenceV1_NormalizedVertex", "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1." }, "confidence": { "description": "The confidence score of the detected landmark. Range [0, 1].", "type": "number", "format": "float" } }, "description": "A generic detected landmark represented by name in string format and a 2D location.", "id": "GoogleCloudVideointelligenceV1_DetectedLandmark", "type": "object" }, "GoogleCloudVideointelligenceV1_VideoAnnotationProgress": { "properties": { "inputUri": { "type": "string", "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)." }, "progressPercent": { "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.", "type": "integer", "format": "int32" }, "updateTime": { "type": "string", "format": "google-datetime", "description": "Time of the most recent update." }, "segment": { "$ref": "GoogleCloudVideointelligenceV1_VideoSegment", "description": "Specifies which segment is being tracked if the request contains more than one segment." }, "startTime": { "type": "string", "format": "google-datetime", "description": "Time when the request was received." }, "feature": { "type": "string", "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "PERSON_DETECTION" ], "description": "Specifies which feature is being tracked if the request contains more than one feature.", "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Person detection." ] }, "exportStatus": { "$ref": "GoogleCloudVideointelligenceV1_ExportToOutputUriStatus", "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request." } }, "description": "Annotation progress for a single video.", "id": "GoogleCloudVideointelligenceV1_VideoAnnotationProgress", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject": { "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.", "id": "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject", "type": "object", "properties": { "normalizedBoundingBox": { "description": "Normalized Bounding box in a frame, where the object is located.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox" }, "timeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object." }, "attributes": { "type": "array", "description": "Optional. The attributes of the object in the bounding box.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute" } }, "landmarks": { "type": "array", "description": "Optional. The detected landmarks.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark" } } } }, "GoogleCloudVideointelligenceV1_ExplicitContentFrame": { "properties": { "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string", "format": "google-duration" }, "pornographyLikelihood": { "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ], "description": "Likelihood of the pornography content..", "type": "string", "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ] } }, "description": "Video frame level annotation results for explicit content.", "id": "GoogleCloudVideointelligenceV1_ExplicitContentFrame", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_TextFrame": { "id": "GoogleCloudVideointelligenceV1p2beta1_TextFrame", "type": "object", "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", "properties": { "rotatedBoundingBox": { "description": "Bounding polygon of the detected text for this frame.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly" }, "timeOffset": { "type": "string", "format": "google-duration", "description": "Timestamp of this frame." } } }, "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation": { "id": "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation", "type": "object", "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", "properties": { "frames": { "type": "array", "description": "All video frames where explicit content was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1_ExplicitContentFrame" } }, "version": { "description": "Feature version.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p1beta1_TextSegment": { "id": "GoogleCloudVideointelligenceV1p1beta1_TextSegment", "type": "object", "description": "Video segment level annotation results for text detection.", "properties": { "segment": { "description": "Video segment where a text snippet was detected.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "frames": { "type": "array", "description": "Information related to the frames where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextFrame" } }, "confidence": { "type": "number", "format": "float", "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears." } } }, "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation": { "id": "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation", "type": "object", "description": "Person detection annotation per video.", "properties": { "tracks": { "type": "array", "description": "The detected tracks of a person.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Track" } }, "version": { "description": "Feature version.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p3beta1_TextDetectionConfig": { "properties": { "languageHints": { "type": "array", "description": "Language hint can be specified if the language to be detected is known a priori. It can increase the accuracy of the detection. Language hint must be language code in BCP-47 format. Automatic language detection is performed if no hint is provided.", "items": { "type": "string" } }, "model": { "description": "Model to use for text detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".", "type": "string" } }, "description": "Config for TEXT_DETECTION.", "id": "GoogleCloudVideointelligenceV1p3beta1_TextDetectionConfig", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation": { "id": "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation", "type": "object", "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", "properties": { "text": { "description": "The detected text.", "type": "string" }, "version": { "type": "string", "description": "Feature version." }, "segments": { "description": "All video segments where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextSegment" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1beta2_SpeechTranscription": { "properties": { "alternatives": { "type": "array", "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative" } }, "languageCode": { "readOnly": true, "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", "type": "string" } }, "description": "A speech recognition result corresponding to a portion of the audio.", "id": "GoogleCloudVideointelligenceV1beta2_SpeechTranscription", "type": "object" }, "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation": { "id": "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation", "type": "object", "description": "Annotations corresponding to one tracked object.", "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1_VideoSegment", "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears." }, "entity": { "$ref": "GoogleCloudVideointelligenceV1_Entity", "description": "Entity to specify the object category that this track is labeled as." }, "frames": { "type": "array", "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1_ObjectTrackingFrame" } }, "trackId": { "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.", "type": "string", "format": "int64" }, "confidence": { "description": "Object category's labeling confidence of this track.", "type": "number", "format": "float" }, "version": { "type": "string", "description": "Feature version." } } }, "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative": { "properties": { "confidence": { "readOnly": true, "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "type": "number", "format": "float" }, "words": { "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_WordInfo" }, "type": "array", "readOnly": true }, "transcript": { "description": "Transcript text representing the words that the user spoke.", "type": "string" } }, "description": "Alternative hypotheses (a.k.a. n-best list).", "id": "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative", "type": "object" }, "GoogleCloudVideointelligenceV1_TextFrame": { "properties": { "rotatedBoundingBox": { "description": "Bounding polygon of the detected text for this frame.", "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly" }, "timeOffset": { "type": "string", "format": "google-duration", "description": "Timestamp of this frame." } }, "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", "id": "GoogleCloudVideointelligenceV1_TextFrame", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_VideoSegment": { "properties": { "endTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", "type": "string", "format": "google-duration" }, "startTimeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive)." } }, "description": "Video segment.", "id": "GoogleCloudVideointelligenceV1beta2_VideoSegment", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute": { "properties": { "confidence": { "type": "number", "format": "float", "description": "Detected attribute confidence. Range [0, 1]." }, "name": { "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", "type": "string" }, "value": { "type": "string", "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc." } }, "description": "A generic detected attribute represented by name in string format.", "id": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_LabelFrame": { "description": "Video frame level annotation results for label detection.", "id": "GoogleCloudVideointelligenceV1p1beta1_LabelFrame", "type": "object", "properties": { "timeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location." }, "confidence": { "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoResponse": { "properties": { "annotationResults": { "type": "array", "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults" } } }, "id": "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoResponse", "type": "object", "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service." }, "GoogleCloudVideointelligenceV1p1beta1_FaceFrame": { "properties": { "normalizedBoundingBoxes": { "type": "array", "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox" } }, "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string", "format": "google-duration" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_FaceFrame", "type": "object", "deprecated": true, "description": "Deprecated. No effect." }, "GoogleCloudVideointelligenceV1_VideoAnnotationResults": { "properties": { "error": { "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.", "$ref": "GoogleRpc_Status" }, "shotAnnotations": { "description": "Shot annotations. Each shot is represented as a video segment.", "items": { "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" }, "type": "array" }, "shotLabelAnnotations": { "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" }, "type": "array" }, "objectAnnotations": { "description": "Annotations for list of objects detected and tracked in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation" }, "type": "array" }, "faceAnnotations": { "description": "Deprecated. Please use `face_detection_annotations` instead.", "items": { "$ref": "GoogleCloudVideointelligenceV1_FaceAnnotation" }, "type": "array", "deprecated": true }, "explicitAnnotation": { "$ref": "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation", "description": "Explicit content annotation." }, "segment": { "$ref": "GoogleCloudVideointelligenceV1_VideoSegment", "description": "Video segment on which the annotation is run." }, "textAnnotations": { "type": "array", "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", "items": { "$ref": "GoogleCloudVideointelligenceV1_TextAnnotation" } }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "frameLabelAnnotations": { "description": "Label annotations on frame level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" }, "type": "array" }, "logoRecognitionAnnotations": { "type": "array", "description": "Annotations for list of logos detected, tracked and recognized in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation" } }, "faceDetectionAnnotations": { "type": "array", "description": "Face detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation" } }, "segmentPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" } }, "shotPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" } }, "personDetectionAnnotations": { "description": "Person detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation" }, "type": "array" }, "speechTranscriptions": { "type": "array", "description": "Speech transcription.", "items": { "$ref": "GoogleCloudVideointelligenceV1_SpeechTranscription" } }, "segmentLabelAnnotations": { "type": "array", "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" } } }, "description": "Annotation results for a single video.", "id": "GoogleCloudVideointelligenceV1_VideoAnnotationResults", "type": "object" }, "GoogleCloudVideointelligenceV1_LabelFrame": { "properties": { "confidence": { "type": "number", "format": "float", "description": "Confidence that the label is accurate. Range: [0, 1]." }, "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string", "format": "google-duration" } }, "id": "GoogleCloudVideointelligenceV1_LabelFrame", "type": "object", "description": "Video frame level annotation results for label detection." }, "GoogleCloudVideointelligenceV1beta2_NormalizedVertex": { "id": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex", "type": "object", "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "properties": { "x": { "type": "number", "format": "float", "description": "X coordinate." }, "y": { "type": "number", "format": "float", "description": "Y coordinate." } } }, "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation": { "properties": { "version": { "description": "Feature version.", "type": "string" }, "frames": { "description": "All video frames where explicit content was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame" }, "type": "array" } }, "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", "id": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription": { "properties": { "languageCode": { "readOnly": true, "type": "string", "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio." }, "alternatives": { "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative" }, "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription", "type": "object", "description": "A speech recognition result corresponding to a portion of the audio." }, "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation": { "description": "Face detection annotation.", "id": "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation", "type": "object", "properties": { "tracks": { "description": "The face tracks with attributes.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_Track" }, "type": "array" }, "thumbnail": { "description": "The thumbnail of a person's face.", "type": "string", "format": "byte" }, "version": { "type": "string", "description": "Feature version." } } }, "GoogleCloudVideointelligenceV1p3beta1_FaceSegment": { "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment", "description": "Video segment where a face was detected." } }, "id": "GoogleCloudVideointelligenceV1p3beta1_FaceSegment", "type": "object", "description": "Video segment level annotation results for face detection." }, "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame": { "properties": { "pornographyLikelihood": { "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ], "type": "string", "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ], "description": "Likelihood of the pornography content.." }, "timeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location." } }, "id": "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame", "type": "object", "description": "Video frame level annotation results for explicit content." }, "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscriptionConfig": { "description": "Config for SPEECH_TRANSCRIPTION.", "id": "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscriptionConfig", "type": "object", "properties": { "diarizationSpeakerCount": { "description": "Optional. If set, specifies the estimated number of speakers in the conversation. If not set, defaults to '2'. Ignored unless enable_speaker_diarization is set to true.", "type": "integer", "format": "int32" }, "languageCode": { "description": "Required. *Required* The language of the supplied audio as a [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. Example: \"en-US\". See [Language Support](https://cloud.google.com/speech/docs/languages) for a list of the currently supported language codes.", "type": "string" }, "enableSpeakerDiarization": { "description": "Optional. If 'true', enables speaker detection for each recognized word in the top alternative of the recognition result using a speaker_tag provided in the WordInfo. Note: When this is true, we send all the words from the beginning of the audio for the top alternative in every consecutive response. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time.", "type": "boolean" }, "audioOutputUriPrefix": { "type": "string", "description": "Optional. Legacy field. This field must be a Cloud Storage URI prefix. (e.g., `gs://bucket/path/`)." }, "enableWordConfidence": { "description": "Optional. If `true`, the top result includes a list of words and the confidence for those words. If `false`, no word-level confidence information is returned. The default is `false`.", "type": "boolean" }, "filterProfanity": { "description": "Optional. If set to `true`, the server will attempt to filter out profanities, replacing all but the initial character in each filtered word with asterisks, e.g. \"f***\". If set to `false` or omitted, profanities won't be filtered out.", "type": "boolean" }, "enableAutomaticPunctuation": { "type": "boolean", "description": "Optional. If 'true', adds punctuation to recognition result hypotheses. This feature is only available in select languages. Setting this for requests in other languages has no effect at all. The default 'false' value does not add punctuation to result hypotheses. NOTE: \"This is currently offered as an experimental service, complimentary to all users. In the future this may be exclusively available as a premium feature.\"" }, "maxAlternatives": { "description": "Optional. Maximum number of recognition hypotheses to be returned. Specifically, the maximum number of `SpeechRecognitionAlternative` messages within each `SpeechTranscription`. The server may return fewer than `max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of one. If omitted, will return a maximum of one.", "type": "integer", "format": "int32" }, "audioTracks": { "description": "Optional. For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two tracks. Default: track 0.", "items": { "type": "integer", "format": "int32" }, "type": "array" }, "speechContexts": { "type": "array", "description": "Optional. A means to provide context to assist the speech recognition.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_SpeechContext" } } } }, "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults": { "properties": { "error": { "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.", "$ref": "GoogleRpc_Status" }, "shotAnnotations": { "description": "Shot annotations. Each shot is represented as a video segment.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "type": "array" }, "shotLabelAnnotations": { "type": "array", "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" } }, "objectAnnotations": { "type": "array", "description": "Annotations for list of objects detected and tracked in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation" } }, "faceAnnotations": { "deprecated": true, "type": "array", "description": "Deprecated. Please use `face_detection_annotations` instead.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_FaceAnnotation" } }, "explicitAnnotation": { "description": "Explicit content annotation.", "$ref": "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation" }, "segment": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment", "description": "Video segment on which the annotation is run." }, "textAnnotations": { "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_TextAnnotation" }, "type": "array" }, "inputUri": { "type": "string", "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)." }, "frameLabelAnnotations": { "description": "Label annotations on frame level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" }, "type": "array" }, "logoRecognitionAnnotations": { "type": "array", "description": "Annotations for list of logos detected, tracked and recognized in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation" } }, "faceDetectionAnnotations": { "type": "array", "description": "Face detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation" } }, "segmentPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" } }, "shotPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" } }, "personDetectionAnnotations": { "type": "array", "description": "Person detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation" } }, "speechTranscriptions": { "description": "Speech transcription.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_SpeechTranscription" }, "type": "array" }, "segmentLabelAnnotations": { "type": "array", "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" } } }, "id": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults", "type": "object", "description": "Annotation results for a single video." }, "GoogleCloudVideointelligenceV1beta2_FaceAnnotation": { "description": "Deprecated. No effect.", "deprecated": true, "id": "GoogleCloudVideointelligenceV1beta2_FaceAnnotation", "type": "object", "properties": { "frames": { "description": "All video frames where a face was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_FaceFrame" }, "type": "array" }, "thumbnail": { "type": "string", "format": "byte", "description": "Thumbnail of a representative face view (in JPEG format)." }, "segments": { "type": "array", "description": "All video segments where a face was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_FaceSegment" } } } }, "GoogleCloudVideointelligenceV1_Entity": { "properties": { "languageCode": { "type": "string", "description": "Language code for `description` in BCP-47 format." }, "entityId": { "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", "type": "string" }, "description": { "description": "Textual description, e.g., `Fixed-gear bicycle`.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1_Entity", "type": "object", "description": "Detected entity from video analysis." }, "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox": { "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox", "type": "object", "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", "properties": { "bottom": { "description": "Bottom Y coordinate.", "type": "number", "format": "float" }, "left": { "description": "Left X coordinate.", "type": "number", "format": "float" }, "top": { "type": "number", "format": "float", "description": "Top Y coordinate." }, "right": { "type": "number", "format": "float", "description": "Right X coordinate." } } }, "GoogleCloudVideointelligenceV1beta2_TextFrame": { "properties": { "rotatedBoundingBox": { "description": "Bounding polygon of the detected text for this frame.", "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly" }, "timeOffset": { "description": "Timestamp of this frame.", "type": "string", "format": "google-duration" } }, "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", "id": "GoogleCloudVideointelligenceV1beta2_TextFrame", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_LabelSegment": { "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", "description": "Video segment where a label was detected." }, "confidence": { "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_LabelSegment", "type": "object", "description": "Video segment level annotation results for label detection." }, "GoogleCloudVideointelligenceV1_ExportToOutputUriStatus": { "properties": { "state": { "type": "string", "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ], "readOnly": true, "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ], "description": "Output only. State of the `output_uri` export." }, "status": { "description": "Output only. Only set if state is FAILED.", "readOnly": true, "$ref": "GoogleRpc_Status" } }, "description": "Status of exporting annotation response to user specified `output_uri`.", "id": "GoogleCloudVideointelligenceV1_ExportToOutputUriStatus", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_TextFrame": { "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", "id": "GoogleCloudVideointelligenceV1p1beta1_TextFrame", "type": "object", "properties": { "rotatedBoundingBox": { "description": "Bounding polygon of the detected text for this frame.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly" }, "timeOffset": { "description": "Timestamp of this frame.", "type": "string", "format": "google-duration" } } }, "GoogleCloudVideointelligenceV1p1beta1_WordInfo": { "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", "id": "GoogleCloudVideointelligenceV1p1beta1_WordInfo", "type": "object", "properties": { "speakerLabel": { "readOnly": true, "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.", "type": "string" }, "speakerTag": { "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "type": "integer", "format": "int32", "readOnly": true }, "startTime": { "type": "string", "format": "google-duration", "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary." }, "word": { "type": "string", "description": "The word corresponding to this set of information." }, "endTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string", "format": "google-duration" }, "confidence": { "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "type": "number", "format": "float", "readOnly": true } } }, "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation": { "properties": { "tracks": { "type": "array", "description": "The detected tracks of a person.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_Track" } }, "version": { "description": "Feature version.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation", "type": "object", "description": "Person detection annotation per video." }, "GoogleCloudVideointelligenceV1_FaceSegment": { "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1_VideoSegment", "description": "Video segment where a face was detected." } }, "description": "Video segment level annotation results for face detection.", "id": "GoogleCloudVideointelligenceV1_FaceSegment", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation": { "description": "Face detection annotation.", "id": "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation", "type": "object", "properties": { "tracks": { "description": "The face tracks with attributes.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track" }, "type": "array" }, "thumbnail": { "description": "The thumbnail of a person's face.", "type": "string", "format": "byte" }, "version": { "description": "Feature version.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation": { "properties": { "entity": { "description": "Detected entity.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity" }, "frames": { "type": "array", "description": "All video frames where a label was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelFrame" } }, "categoryEntities": { "type": "array", "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity" } }, "version": { "description": "Feature version.", "type": "string" }, "segments": { "description": "All video segments where a label was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelSegment" }, "type": "array" } }, "description": "Label annotation.", "id": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame": { "properties": { "pornographyLikelihood": { "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ], "type": "string", "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ], "description": "Likelihood of the pornography content.." }, "timeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location." } }, "id": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame", "type": "object", "description": "Video frame level annotation results for explicit content." }, "GoogleCloudVideointelligenceV1p3beta1_LabelFrame": { "properties": { "confidence": { "type": "number", "format": "float", "description": "Confidence that the label is accurate. Range: [0, 1]." }, "timeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location." } }, "description": "Video frame level annotation results for label detection.", "id": "GoogleCloudVideointelligenceV1p3beta1_LabelFrame", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_ExportToOutputUriStatus": { "properties": { "state": { "type": "string", "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ], "readOnly": true, "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ], "description": "Output only. State of the `output_uri` export." }, "status": { "readOnly": true, "$ref": "GoogleRpc_Status", "description": "Output only. Only set if state is FAILED." } }, "id": "GoogleCloudVideointelligenceV1p3beta1_ExportToOutputUriStatus", "type": "object", "description": "Status of exporting annotation response to user specified `output_uri`." }, "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame": { "properties": { "timeOffset": { "description": "The timestamp of the frame in microseconds.", "type": "string", "format": "google-duration" }, "normalizedBoundingBox": { "description": "The normalized bounding box location of this object track for the frame.", "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox" } }, "id": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame", "type": "object", "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence." }, "GoogleCloudVideointelligenceV1beta2_Entity": { "description": "Detected entity from video analysis.", "id": "GoogleCloudVideointelligenceV1beta2_Entity", "type": "object", "properties": { "languageCode": { "description": "Language code for `description` in BCP-47 format.", "type": "string" }, "entityId": { "type": "string", "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/)." }, "description": { "description": "Textual description, e.g., `Fixed-gear bicycle`.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation": { "description": "Label annotation.", "id": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation", "type": "object", "properties": { "entity": { "description": "Detected entity.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity" }, "frames": { "type": "array", "description": "All video frames where a label was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelFrame" } }, "segments": { "description": "All video segments where a label was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelSegment" }, "type": "array" }, "categoryEntities": { "type": "array", "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity" } }, "version": { "type": "string", "description": "Feature version." } } }, "GoogleCloudVideointelligenceV1_VideoSegment": { "properties": { "startTimeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive)." }, "endTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", "type": "string", "format": "google-duration" } }, "id": "GoogleCloudVideointelligenceV1_VideoSegment", "type": "object", "description": "Video segment." }, "GoogleCloudVideointelligenceV1p1beta1_Track": { "description": "A track of an object instance.", "id": "GoogleCloudVideointelligenceV1p1beta1_Track", "type": "object", "properties": { "confidence": { "description": "Optional. The confidence score of the tracked object.", "type": "number", "format": "float" }, "timestampedObjects": { "type": "array", "description": "The object with timestamp and attributes per frame in the track.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject" } }, "attributes": { "type": "array", "description": "Optional. Attributes in the track level.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute" } }, "segment": { "description": "Video segment of a track.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" } } }, "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation": { "properties": { "segments": { "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "type": "array" }, "tracks": { "type": "array", "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Track" } }, "entity": { "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation", "type": "object", "description": "Annotation corresponding to one detected, tracked and recognized logo class." }, "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoResponse": { "id": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoResponse", "type": "object", "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "properties": { "annotationResults": { "type": "array", "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults" } } } }, "GoogleCloudVideointelligenceV1beta2_LabelAnnotation": { "properties": { "categoryEntities": { "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_Entity" }, "type": "array" }, "version": { "description": "Feature version.", "type": "string" }, "segments": { "type": "array", "description": "All video segments where a label was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelSegment" } }, "entity": { "description": "Detected entity.", "$ref": "GoogleCloudVideointelligenceV1beta2_Entity" }, "frames": { "description": "All video frames where a label was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelFrame" }, "type": "array" } }, "description": "Label annotation.", "id": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_TextSegment": { "description": "Video segment level annotation results for text detection.", "id": "GoogleCloudVideointelligenceV1p3beta1_TextSegment", "type": "object", "properties": { "confidence": { "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", "type": "number", "format": "float" }, "segment": { "description": "Video segment where a text snippet was detected.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "frames": { "description": "Information related to the frames where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextFrame" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1_NormalizedBoundingBox": { "properties": { "bottom": { "description": "Bottom Y coordinate.", "type": "number", "format": "float" }, "left": { "type": "number", "format": "float", "description": "Left X coordinate." }, "top": { "type": "number", "format": "float", "description": "Top Y coordinate." }, "right": { "type": "number", "format": "float", "description": "Right X coordinate." } }, "id": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox", "type": "object", "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1]." }, "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation": { "properties": { "segments": { "type": "array", "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" } }, "entity": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity", "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as." }, "tracks": { "type": "array", "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_Track" } } }, "id": "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation", "type": "object", "description": "Annotation corresponding to one detected, tracked and recognized logo class." }, "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults": { "description": "Annotation results for a single video.", "id": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults", "type": "object", "properties": { "explicitAnnotation": { "description": "Explicit content annotation.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation" }, "segment": { "description": "Video segment on which the annotation is run.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "textAnnotations": { "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation" }, "type": "array" }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "frameLabelAnnotations": { "description": "Label annotations on frame level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" }, "type": "array" }, "logoRecognitionAnnotations": { "type": "array", "description": "Annotations for list of logos detected, tracked and recognized in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation" } }, "error": { "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.", "$ref": "GoogleRpc_Status" }, "shotAnnotations": { "type": "array", "description": "Shot annotations. Each shot is represented as a video segment.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" } }, "celebrityRecognitionAnnotations": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation", "description": "Celebrity recognition annotations." }, "shotLabelAnnotations": { "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" }, "type": "array" }, "objectAnnotations": { "type": "array", "description": "Annotations for list of objects detected and tracked in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation" } }, "faceAnnotations": { "type": "array", "description": "Deprecated. Please use `face_detection_annotations` instead.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation" }, "deprecated": true }, "speechTranscriptions": { "description": "Speech transcription.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription" }, "type": "array" }, "segmentLabelAnnotations": { "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" }, "type": "array" }, "faceDetectionAnnotations": { "description": "Face detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation" }, "type": "array" }, "segmentPresenceLabelAnnotations": { "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" }, "type": "array" }, "shotPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" } }, "personDetectionAnnotations": { "description": "Person detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1beta2_AnnotateVideoProgress": { "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "id": "GoogleCloudVideointelligenceV1beta2_AnnotateVideoProgress", "type": "object", "properties": { "annotationProgress": { "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p1beta1_Entity": { "id": "GoogleCloudVideointelligenceV1p1beta1_Entity", "type": "object", "description": "Detected entity from video analysis.", "properties": { "entityId": { "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", "type": "string" }, "description": { "description": "Textual description, e.g., `Fixed-gear bicycle`.", "type": "string" }, "languageCode": { "description": "Language code for `description` in BCP-47 format.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p2beta1_VideoSegment": { "properties": { "endTimeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive)." }, "startTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", "type": "string", "format": "google-duration" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", "type": "object", "description": "Video segment." }, "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly": { "properties": { "vertices": { "type": "array", "description": "Normalized vertices of the bounding polygon.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex" } } }, "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.", "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation": { "id": "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation", "type": "object", "properties": { "thumbnail": { "description": "Thumbnail of a representative face view (in JPEG format).", "type": "string", "format": "byte" }, "frames": { "description": "All video frames where a face was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceFrame" }, "type": "array" }, "segments": { "description": "All video segments where a face was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceSegment" }, "type": "array" } }, "description": "Deprecated. No effect.", "deprecated": true }, "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoRequest": { "id": "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoRequest", "type": "object", "description": "Video annotation request.", "properties": { "videoContext": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoContext", "description": "Additional video context and/or feature-specific parameters." }, "locationId": { "type": "string", "description": "Optional. Cloud region where annotation should take place. Supported cloud regions are: `us-east1`, `us-west1`, `europe-west1`, `asia-east1`. If no region is specified, the region will be determined based on video file location." }, "inputUri": { "type": "string", "description": "Input video location. Currently, only [Cloud Storage](https://cloud.google.com/storage/) URIs are supported. URIs must be specified in the following format: `gs://bucket-id/object-id` (other URI formats return google.rpc.Code.INVALID_ARGUMENT). For more information, see [Request URIs](https://cloud.google.com/storage/docs/request-endpoints). To identify multiple videos, a video URI may include wildcards in the `object-id`. Supported wildcards: '*' to match 0 or more characters; '?' to match 1 character. If unset, the input video should be embedded in the request as `input_content`. If set, `input_content` must be unset." }, "inputContent": { "description": "The video data bytes. If unset, the input video(s) should be specified via the `input_uri`. If set, `input_uri` must be unset.", "type": "string", "format": "byte" }, "outputUri": { "description": "Optional. Location where the output (in JSON format) should be stored. Currently, only [Cloud Storage](https://cloud.google.com/storage/) URIs are supported. These must be specified in the following format: `gs://bucket-id/object-id` (other URI formats return google.rpc.Code.INVALID_ARGUMENT). For more information, see [Request URIs](https://cloud.google.com/storage/docs/request-endpoints).", "type": "string" }, "features": { "type": "array", "description": "Required. Requested video annotation features.", "items": { "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Celebrity recognition.", "Person detection." ], "type": "string", "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "CELEBRITY_RECOGNITION", "PERSON_DETECTION" ] } } } }, "GoogleCloudVideointelligenceV1_NormalizedVertex": { "properties": { "x": { "description": "X coordinate.", "type": "number", "format": "float" }, "y": { "description": "Y coordinate.", "type": "number", "format": "float" } }, "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "id": "GoogleCloudVideointelligenceV1_NormalizedVertex", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_Celebrity": { "id": "GoogleCloudVideointelligenceV1p3beta1_Celebrity", "type": "object", "description": "Celebrity definition.", "properties": { "name": { "type": "string", "description": "The resource name of the celebrity. Have the format `video-intelligence/kg-mid` indicates a celebrity from preloaded gallery. kg-mid is the id in Google knowledge graph, which is unique for the celebrity." }, "displayName": { "description": "The celebrity name.", "type": "string" }, "description": { "description": "Textual description of additional information about the celebrity, if applicable.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p1beta1_VideoSegment": { "properties": { "startTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", "type": "string", "format": "google-duration" }, "endTimeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive)." } }, "id": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment", "type": "object", "description": "Video segment." }, "GoogleCloudVideointelligenceV1p2beta1_FaceFrame": { "properties": { "normalizedBoundingBoxes": { "type": "array", "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox" } }, "timeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location." } }, "id": "GoogleCloudVideointelligenceV1p2beta1_FaceFrame", "type": "object", "deprecated": true, "description": "Deprecated. No effect." }, "GoogleCloudVideointelligenceV1p3beta1_FaceFrame": { "properties": { "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string", "format": "google-duration" }, "normalizedBoundingBoxes": { "type": "array", "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox" } } }, "id": "GoogleCloudVideointelligenceV1p3beta1_FaceFrame", "type": "object", "deprecated": true, "description": "Deprecated. No effect." }, "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation": { "id": "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation", "type": "object", "description": "Person detection annotation per video.", "properties": { "tracks": { "description": "The detected tracks of a person.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track" }, "type": "array" }, "version": { "description": "Feature version.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame": { "properties": { "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string", "format": "google-duration" }, "pornographyLikelihood": { "description": "Likelihood of the pornography content..", "type": "string", "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ], "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ] } }, "id": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame", "type": "object", "description": "Video frame level annotation results for explicit content." }, "GoogleCloudVideointelligenceV1p3beta1_Track": { "description": "A track of an object instance.", "id": "GoogleCloudVideointelligenceV1p3beta1_Track", "type": "object", "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment", "description": "Video segment of a track." }, "timestampedObjects": { "description": "The object with timestamp and attributes per frame in the track.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject" }, "type": "array" }, "attributes": { "description": "Optional. Attributes in the track level.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute" }, "type": "array" }, "confidence": { "description": "Optional. The confidence score of the tracked object.", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1p1beta1_ExportToOutputUriStatus": { "properties": { "state": { "readOnly": true, "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ], "type": "string", "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ], "description": "Output only. State of the `output_uri` export." }, "status": { "description": "Output only. Only set if state is FAILED.", "readOnly": true, "$ref": "GoogleRpc_Status" } }, "description": "Status of exporting annotation response to user specified `output_uri`.", "id": "GoogleCloudVideointelligenceV1p1beta1_ExportToOutputUriStatus", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack": { "properties": { "faceTrack": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track", "description": "A track of a person's face." }, "celebrities": { "description": "Top N match of the celebrities for the face in this track.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity" }, "type": "array" } }, "description": "The annotation result of a celebrity face track. RecognizedCelebrity field could be empty if the face track does not have any matched celebrities.", "id": "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress": { "description": "Annotation progress for a single video.", "id": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress", "type": "object", "properties": { "startTime": { "description": "Time when the request was received.", "type": "string", "format": "google-datetime" }, "feature": { "type": "string", "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "PERSON_DETECTION" ], "description": "Specifies which feature is being tracked if the request contains more than one feature.", "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Person detection." ] }, "segment": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", "description": "Specifies which segment is being tracked if the request contains more than one segment." }, "inputUri": { "type": "string", "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)." }, "progressPercent": { "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.", "type": "integer", "format": "int32" }, "updateTime": { "type": "string", "format": "google-datetime", "description": "Time of the most recent update." }, "exportStatus": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExportToOutputUriStatus", "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request." } } }, "GoogleCloudVideointelligenceV1beta2_LabelFrame": { "description": "Video frame level annotation results for label detection.", "id": "GoogleCloudVideointelligenceV1beta2_LabelFrame", "type": "object", "properties": { "confidence": { "type": "number", "format": "float", "description": "Confidence that the label is accurate. Range: [0, 1]." }, "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string", "format": "google-duration" } } }, "GoogleCloudVideointelligenceV1_TextAnnotation": { "properties": { "segments": { "type": "array", "description": "All video segments where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1_TextSegment" } }, "text": { "description": "The detected text.", "type": "string" }, "version": { "description": "Feature version.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1_TextAnnotation", "type": "object", "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection." }, "GoogleCloudVideointelligenceV1p3beta1_ShotChangeDetectionConfig": { "description": "Config for SHOT_CHANGE_DETECTION.", "id": "GoogleCloudVideointelligenceV1p3beta1_ShotChangeDetectionConfig", "type": "object", "properties": { "model": { "type": "string", "description": "Model to use for shot change detection. Supported values: \"builtin/stable\" (the default if unset), \"builtin/latest\", and \"builtin/legacy\"." } } }, "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation": { "properties": { "tracks": { "description": "The face tracks with attributes.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_Track" }, "type": "array" }, "thumbnail": { "description": "The thumbnail of a person's face.", "type": "string", "format": "byte" }, "version": { "type": "string", "description": "Feature version." } }, "id": "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation", "type": "object", "description": "Face detection annotation." }, "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation": { "description": "Deprecated. No effect.", "deprecated": true, "id": "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation", "type": "object", "properties": { "segments": { "type": "array", "description": "All video segments where a face was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceSegment" } }, "thumbnail": { "description": "Thumbnail of a representative face view (in JPEG format).", "type": "string", "format": "byte" }, "frames": { "description": "All video frames where a face was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceFrame" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1beta2_FaceSegment": { "id": "GoogleCloudVideointelligenceV1beta2_FaceSegment", "type": "object", "description": "Video segment level annotation results for face detection.", "properties": { "segment": { "description": "Video segment where a face was detected.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" } } }, "GoogleCloudVideointelligenceV1beta2_TextSegment": { "properties": { "confidence": { "type": "number", "format": "float", "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears." }, "segment": { "description": "Video segment where a text snippet was detected.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "frames": { "type": "array", "description": "Information related to the frames where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_TextFrame" } } }, "id": "GoogleCloudVideointelligenceV1beta2_TextSegment", "type": "object", "description": "Video segment level annotation results for text detection." }, "GoogleCloudVideointelligenceV1_SpeechTranscription": { "id": "GoogleCloudVideointelligenceV1_SpeechTranscription", "type": "object", "description": "A speech recognition result corresponding to a portion of the audio.", "properties": { "alternatives": { "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", "items": { "$ref": "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative" }, "type": "array" }, "languageCode": { "type": "string", "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", "readOnly": true } } }, "GoogleCloudVideointelligenceV1_DetectedAttribute": { "properties": { "value": { "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.", "type": "string" }, "name": { "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", "type": "string" }, "confidence": { "type": "number", "format": "float", "description": "Detected attribute confidence. Range [0, 1]." } }, "description": "A generic detected attribute represented by name in string format.", "id": "GoogleCloudVideointelligenceV1_DetectedAttribute", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative": { "id": "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative", "type": "object", "description": "Alternative hypotheses (a.k.a. n-best list).", "properties": { "transcript": { "type": "string", "description": "Transcript text representing the words that the user spoke." }, "confidence": { "type": "number", "format": "float", "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true }, "words": { "readOnly": true, "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_WordInfo" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1beta2_WordInfo": { "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", "id": "GoogleCloudVideointelligenceV1beta2_WordInfo", "type": "object", "properties": { "speakerTag": { "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "type": "integer", "format": "int32", "readOnly": true }, "startTime": { "type": "string", "format": "google-duration", "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary." }, "speakerLabel": { "readOnly": true, "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.", "type": "string" }, "word": { "type": "string", "description": "The word corresponding to this set of information." }, "endTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string", "format": "google-duration" }, "confidence": { "type": "number", "format": "float", "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true } } }, "GoogleCloudVideointelligenceV1beta2_TimestampedObject": { "properties": { "normalizedBoundingBox": { "description": "Normalized Bounding box in a frame, where the object is located.", "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox" }, "timeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object." }, "attributes": { "type": "array", "description": "Optional. The attributes of the object in the bounding box.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute" } }, "landmarks": { "type": "array", "description": "Optional. The detected landmarks.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedLandmark" } } }, "id": "GoogleCloudVideointelligenceV1beta2_TimestampedObject", "type": "object", "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box." }, "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame": { "properties": { "normalizedBoundingBox": { "description": "The normalized bounding box location of this object track for the frame.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox" }, "timeOffset": { "description": "The timestamp of the frame in microseconds.", "type": "string", "format": "google-duration" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame", "type": "object", "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence." }, "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly": { "properties": { "vertices": { "description": "Normalized vertices of the bounding polygon.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex" }, "type": "array" } }, "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.", "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation": { "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears." }, "entity": { "description": "Entity to specify the object category that this track is labeled as.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity" }, "frames": { "type": "array", "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame" } }, "version": { "description": "Feature version.", "type": "string" }, "trackId": { "type": "string", "format": "int64", "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time." }, "confidence": { "type": "number", "format": "float", "description": "Object category's labeling confidence of this track." } }, "description": "Annotations corresponding to one tracked object.", "id": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation", "type": "object" }, "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation": { "properties": { "tracks": { "description": "The face tracks with attributes.", "items": { "$ref": "GoogleCloudVideointelligenceV1_Track" }, "type": "array" }, "thumbnail": { "description": "The thumbnail of a person's face.", "type": "string", "format": "byte" }, "version": { "description": "Feature version.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation", "type": "object", "description": "Face detection annotation." }, "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults": { "id": "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults", "type": "object", "description": "Streaming annotation results corresponding to a portion of the video that is currently being processed. Only ONE type of annotation will be specified in the response.", "properties": { "objectAnnotations": { "description": "Object tracking results.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation" }, "type": "array" }, "shotAnnotations": { "description": "Shot annotation results. Each shot is represented as a video segment.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "type": "array" }, "frameTimestamp": { "type": "string", "format": "google-duration", "description": "Timestamp of the processed frame in microseconds." }, "explicitAnnotation": { "description": "Explicit content annotation results.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation" }, "labelAnnotations": { "type": "array", "description": "Label annotation results.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" } } } }, "GoogleCloudVideointelligenceV1_AnnotateVideoResponse": { "id": "GoogleCloudVideointelligenceV1_AnnotateVideoResponse", "type": "object", "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "properties": { "annotationResults": { "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1_VideoAnnotationResults" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoResponse": { "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "id": "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoResponse", "type": "object", "properties": { "annotationResults": { "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress": { "properties": { "exportStatus": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExportToOutputUriStatus", "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request." }, "startTime": { "type": "string", "format": "google-datetime", "description": "Time when the request was received." }, "feature": { "type": "string", "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "CELEBRITY_RECOGNITION", "PERSON_DETECTION" ], "description": "Specifies which feature is being tracked if the request contains more than one feature.", "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Celebrity recognition.", "Person detection." ] }, "segment": { "description": "Specifies which segment is being tracked if the request contains more than one segment.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "inputUri": { "type": "string", "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)." }, "progressPercent": { "type": "integer", "format": "int32", "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed." }, "updateTime": { "description": "Time of the most recent update.", "type": "string", "format": "google-datetime" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress", "type": "object", "description": "Annotation progress for a single video." }, "GoogleCloudVideointelligenceV1p2beta1_LabelFrame": { "description": "Video frame level annotation results for label detection.", "id": "GoogleCloudVideointelligenceV1p2beta1_LabelFrame", "type": "object", "properties": { "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string", "format": "google-duration" }, "confidence": { "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1p2beta1_WordInfo": { "id": "GoogleCloudVideointelligenceV1p2beta1_WordInfo", "type": "object", "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", "properties": { "speakerTag": { "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "type": "integer", "format": "int32", "readOnly": true }, "startTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string", "format": "google-duration" }, "speakerLabel": { "readOnly": true, "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.", "type": "string" }, "word": { "type": "string", "description": "The word corresponding to this set of information." }, "endTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string", "format": "google-duration" }, "confidence": { "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "type": "number", "format": "float", "readOnly": true } } }, "GoogleCloudVideointelligenceV1_TextSegment": { "id": "GoogleCloudVideointelligenceV1_TextSegment", "type": "object", "description": "Video segment level annotation results for text detection.", "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1_VideoSegment", "description": "Video segment where a text snippet was detected." }, "frames": { "description": "Information related to the frames where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1_TextFrame" }, "type": "array" }, "confidence": { "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoProgress": { "properties": { "annotationProgress": { "type": "array", "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress" } } }, "id": "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoProgress", "type": "object", "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service." }, "GoogleCloudVideointelligenceV1_FaceAnnotation": { "description": "Deprecated. No effect.", "deprecated": true, "id": "GoogleCloudVideointelligenceV1_FaceAnnotation", "type": "object", "properties": { "frames": { "description": "All video frames where a face was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1_FaceFrame" }, "type": "array" }, "thumbnail": { "type": "string", "format": "byte", "description": "Thumbnail of a representative face view (in JPEG format)." }, "segments": { "type": "array", "description": "All video segments where a face was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1_FaceSegment" } } } }, "GoogleCloudVideointelligenceV1beta2_DetectedLandmark": { "id": "GoogleCloudVideointelligenceV1beta2_DetectedLandmark", "type": "object", "description": "A generic detected landmark represented by name in string format and a 2D location.", "properties": { "point": { "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.", "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex" }, "confidence": { "type": "number", "format": "float", "description": "The confidence score of the detected landmark. Range [0, 1]." }, "name": { "type": "string", "description": "The name of this landmark, for example, left_hand, right_shoulder." } } }, "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation": { "id": "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation", "type": "object", "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", "properties": { "text": { "type": "string", "description": "The detected text." }, "version": { "description": "Feature version.", "type": "string" }, "segments": { "type": "array", "description": "All video segments where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextSegment" } } } }, "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation": { "id": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation", "type": "object", "description": "Annotations corresponding to one tracked object.", "properties": { "trackId": { "type": "string", "format": "int64", "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time." }, "confidence": { "type": "number", "format": "float", "description": "Object category's labeling confidence of this track." }, "version": { "type": "string", "description": "Feature version." }, "segment": { "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "entity": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity", "description": "Entity to specify the object category that this track is labeled as." }, "frames": { "type": "array", "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame" } } } }, "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex": { "properties": { "x": { "description": "X coordinate.", "type": "number", "format": "float" }, "y": { "description": "Y coordinate.", "type": "number", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex", "type": "object", "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1." }, "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription": { "id": "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription", "type": "object", "description": "A speech recognition result corresponding to a portion of the audio.", "properties": { "alternatives": { "type": "array", "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative" } }, "languageCode": { "readOnly": true, "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation": { "id": "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation", "type": "object", "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", "properties": { "text": { "description": "The detected text.", "type": "string" }, "version": { "type": "string", "description": "Feature version." }, "segments": { "type": "array", "description": "All video segments where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextSegment" } } } }, "GoogleCloudVideointelligenceV1p3beta1_LabelSegment": { "description": "Video segment level annotation results for label detection.", "id": "GoogleCloudVideointelligenceV1p3beta1_LabelSegment", "type": "object", "properties": { "segment": { "description": "Video segment where a label was detected.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "confidence": { "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly": { "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.", "id": "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly", "type": "object", "properties": { "vertices": { "description": "Normalized vertices of the bounding polygon.", "items": { "$ref": "GoogleCloudVideointelligenceV1_NormalizedVertex" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p2beta1_FaceSegment": { "properties": { "segment": { "description": "Video segment where a face was detected.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" } }, "description": "Video segment level annotation results for face detection.", "id": "GoogleCloudVideointelligenceV1p2beta1_FaceSegment", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_TextSegment": { "id": "GoogleCloudVideointelligenceV1p2beta1_TextSegment", "type": "object", "description": "Video segment level annotation results for text detection.", "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", "description": "Video segment where a text snippet was detected." }, "frames": { "type": "array", "description": "Information related to the frames where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextFrame" } }, "confidence": { "type": "number", "format": "float", "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears." } } }, "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex": { "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex", "type": "object", "properties": { "x": { "type": "number", "format": "float", "description": "X coordinate." }, "y": { "type": "number", "format": "float", "description": "Y coordinate." } } }, "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity": { "properties": { "celebrity": { "description": "The recognized celebrity.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_Celebrity" }, "confidence": { "description": "Recognition confidence. Range [0, 1].", "type": "number", "format": "float" } }, "description": "The recognized celebrity with confidence score.", "id": "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_Entity": { "id": "GoogleCloudVideointelligenceV1p2beta1_Entity", "type": "object", "description": "Detected entity from video analysis.", "properties": { "entityId": { "type": "string", "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/)." }, "description": { "type": "string", "description": "Textual description, e.g., `Fixed-gear bicycle`." }, "languageCode": { "type": "string", "description": "Language code for `description` in BCP-47 format." } } }, "GoogleCloudVideointelligenceV1p3beta1_StreamingAnnotateVideoResponse": { "properties": { "annotationResults": { "description": "Streaming annotation results.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults" }, "error": { "$ref": "GoogleRpc_Status", "description": "If set, returns a google.rpc.Status message that specifies the error for the operation." }, "annotationResultsUri": { "type": "string", "description": "Google Cloud Storage URI that stores annotation results of one streaming session in JSON format. It is the annotation_result_storage_directory from the request followed by '/cloud_project_number-session_id'." } }, "id": "GoogleCloudVideointelligenceV1p3beta1_StreamingAnnotateVideoResponse", "type": "object", "description": "`StreamingAnnotateVideoResponse` is the only message returned to the client by `StreamingAnnotateVideo`. A series of zero or more `StreamingAnnotateVideoResponse` messages are streamed back to the client." }, "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame": { "description": "Video frame level annotation results for explicit content.", "id": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame", "type": "object", "properties": { "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string", "format": "google-duration" }, "pornographyLikelihood": { "type": "string", "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ], "description": "Likelihood of the pornography content..", "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ] } } }, "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative": { "description": "Alternative hypotheses (a.k.a. n-best list).", "id": "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative", "type": "object", "properties": { "transcript": { "description": "Transcript text representing the words that the user spoke.", "type": "string" }, "confidence": { "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "type": "number", "format": "float", "readOnly": true }, "words": { "readOnly": true, "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", "items": { "$ref": "GoogleCloudVideointelligenceV1_WordInfo" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation": { "properties": { "tracks": { "type": "array", "description": "The detected tracks of a person.", "items": { "$ref": "GoogleCloudVideointelligenceV1_Track" } }, "version": { "description": "Feature version.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation", "type": "object", "description": "Person detection annotation per video." }, "GoogleCloudVideointelligenceV1p3beta1_Entity": { "properties": { "entityId": { "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", "type": "string" }, "description": { "description": "Textual description, e.g., `Fixed-gear bicycle`.", "type": "string" }, "languageCode": { "type": "string", "description": "Language code for `description` in BCP-47 format." } }, "id": "GoogleCloudVideointelligenceV1p3beta1_Entity", "type": "object", "description": "Detected entity from video analysis." }, "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription": { "description": "A speech recognition result corresponding to a portion of the audio.", "id": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription", "type": "object", "properties": { "languageCode": { "readOnly": true, "type": "string", "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio." }, "alternatives": { "type": "array", "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative" } } } }, "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex": { "properties": { "x": { "type": "number", "format": "float", "description": "X coordinate." }, "y": { "type": "number", "format": "float", "description": "Y coordinate." } }, "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex", "type": "object" }, "GoogleCloudVideointelligenceV1_ObjectTrackingFrame": { "id": "GoogleCloudVideointelligenceV1_ObjectTrackingFrame", "type": "object", "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.", "properties": { "timeOffset": { "description": "The timestamp of the frame in microseconds.", "type": "string", "format": "google-duration" }, "normalizedBoundingBox": { "description": "The normalized bounding box location of this object track for the frame.", "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox" } } }, "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionConfig": { "description": "Config for FACE_DETECTION.", "id": "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionConfig", "type": "object", "properties": { "model": { "description": "Model to use for face detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".", "type": "string" }, "includeAttributes": { "description": "Whether to enable face attributes detection, such as glasses, dark_glasses, mouth_open etc. Ignored if 'include_bounding_boxes' is set to false.", "type": "boolean" }, "includeBoundingBoxes": { "type": "boolean", "description": "Whether bounding boxes are included in the face annotation output." } } }, "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark": { "properties": { "point": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex", "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1." }, "confidence": { "description": "The confidence score of the detected landmark. Range [0, 1].", "type": "number", "format": "float" }, "name": { "type": "string", "description": "The name of this landmark, for example, left_hand, right_shoulder." } }, "description": "A generic detected landmark represented by name in string format and a 2D location.", "id": "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation": { "description": "Label annotation.", "id": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation", "type": "object", "properties": { "segments": { "description": "All video segments where a label was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelSegment" }, "type": "array" }, "categoryEntities": { "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity" }, "type": "array" }, "version": { "description": "Feature version.", "type": "string" }, "entity": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity", "description": "Detected entity." }, "frames": { "description": "All video frames where a label was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelFrame" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject": { "properties": { "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.", "type": "string", "format": "google-duration" }, "attributes": { "description": "Optional. The attributes of the object in the bounding box.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute" }, "type": "array" }, "landmarks": { "type": "array", "description": "Optional. The detected landmarks.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark" } }, "normalizedBoundingBox": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox", "description": "Normalized Bounding box in a frame, where the object is located." } }, "id": "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject", "type": "object", "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box." }, "GoogleCloudVideointelligenceV1beta2_ExportToOutputUriStatus": { "properties": { "state": { "description": "Output only. State of the `output_uri` export.", "readOnly": true, "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ], "type": "string", "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ] }, "status": { "description": "Output only. Only set if state is FAILED.", "readOnly": true, "$ref": "GoogleRpc_Status" } }, "id": "GoogleCloudVideointelligenceV1beta2_ExportToOutputUriStatus", "type": "object", "description": "Status of exporting annotation response to user specified `output_uri`." }, "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoProgress": { "id": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoProgress", "type": "object", "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "properties": { "annotationProgress": { "type": "array", "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress" } } } }, "GoogleCloudVideointelligenceV1p3beta1_VideoContext": { "properties": { "textDetectionConfig": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextDetectionConfig", "description": "Config for TEXT_DETECTION." }, "segments": { "description": "Video segments to annotate. The segments may overlap and are not required to be contiguous or span the whole video. If unspecified, each video is treated as a single segment.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "type": "array" }, "personDetectionConfig": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionConfig", "description": "Config for PERSON_DETECTION." }, "shotChangeDetectionConfig": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ShotChangeDetectionConfig", "description": "Config for SHOT_CHANGE_DETECTION." }, "objectTrackingConfig": { "description": "Config for OBJECT_TRACKING.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingConfig" }, "labelDetectionConfig": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelDetectionConfig", "description": "Config for LABEL_DETECTION." }, "explicitContentDetectionConfig": { "description": "Config for EXPLICIT_CONTENT_DETECTION.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentDetectionConfig" }, "faceDetectionConfig": { "description": "Config for FACE_DETECTION.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionConfig" }, "speechTranscriptionConfig": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscriptionConfig", "description": "Config for SPEECH_TRANSCRIPTION." } }, "id": "GoogleCloudVideointelligenceV1p3beta1_VideoContext", "type": "object", "description": "Video context and/or feature-specific parameters." }, "GoogleCloudVideointelligenceV1beta2_FaceFrame": { "deprecated": true, "description": "Deprecated. No effect.", "properties": { "normalizedBoundingBoxes": { "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox" }, "type": "array" }, "timeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location." } }, "id": "GoogleCloudVideointelligenceV1beta2_FaceFrame", "type": "object" }, "GoogleCloudVideointelligenceV1_LabelSegment": { "id": "GoogleCloudVideointelligenceV1_LabelSegment", "type": "object", "description": "Video segment level annotation results for label detection.", "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1_VideoSegment", "description": "Video segment where a label was detected." }, "confidence": { "type": "number", "format": "float", "description": "Confidence that the label is accurate. Range: [0, 1]." } } }, "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults": { "description": "Annotation results for a single video.", "id": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults", "type": "object", "properties": { "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "segment": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", "description": "Video segment on which the annotation is run." }, "textAnnotations": { "type": "array", "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation" } }, "frameLabelAnnotations": { "type": "array", "description": "Label annotations on frame level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" } }, "logoRecognitionAnnotations": { "description": "Annotations for list of logos detected, tracked and recognized in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation" }, "type": "array" }, "explicitAnnotation": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation", "description": "Explicit content annotation." }, "faceAnnotations": { "description": "Deprecated. Please use `face_detection_annotations` instead.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation" }, "type": "array", "deprecated": true }, "shotLabelAnnotations": { "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" }, "type": "array" }, "objectAnnotations": { "description": "Annotations for list of objects detected and tracked in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation" }, "type": "array" }, "error": { "$ref": "GoogleRpc_Status", "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail." }, "shotAnnotations": { "type": "array", "description": "Shot annotations. Each shot is represented as a video segment.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" } }, "speechTranscriptions": { "type": "array", "description": "Speech transcription.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription" } }, "segmentLabelAnnotations": { "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" }, "type": "array" }, "shotPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" } }, "personDetectionAnnotations": { "type": "array", "description": "Person detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation" } }, "faceDetectionAnnotations": { "type": "array", "description": "Face detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation" } }, "segmentPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" } } } }, "GoogleCloudVideointelligenceV1beta2_TextAnnotation": { "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", "id": "GoogleCloudVideointelligenceV1beta2_TextAnnotation", "type": "object", "properties": { "segments": { "type": "array", "description": "All video segments where OCR detected text appears.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_TextSegment" } }, "version": { "type": "string", "description": "Feature version." }, "text": { "type": "string", "description": "The detected text." } } }, "GoogleCloudVideointelligenceV1p3beta1_VideoSegment": { "properties": { "startTimeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive)." }, "endTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", "type": "string", "format": "google-duration" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment", "type": "object", "description": "Video segment." }, "GoogleCloudVideointelligenceV1_TimestampedObject": { "properties": { "normalizedBoundingBox": { "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox", "description": "Normalized Bounding box in a frame, where the object is located." }, "timeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object." }, "attributes": { "type": "array", "description": "Optional. The attributes of the object in the bounding box.", "items": { "$ref": "GoogleCloudVideointelligenceV1_DetectedAttribute" } }, "landmarks": { "description": "Optional. The detected landmarks.", "items": { "$ref": "GoogleCloudVideointelligenceV1_DetectedLandmark" }, "type": "array" } }, "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.", "id": "GoogleCloudVideointelligenceV1_TimestampedObject", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark": { "properties": { "point": { "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex" }, "confidence": { "type": "number", "format": "float", "description": "The confidence score of the detected landmark. Range [0, 1]." }, "name": { "type": "string", "description": "The name of this landmark, for example, left_hand, right_shoulder." } }, "id": "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark", "type": "object", "description": "A generic detected landmark represented by name in string format and a 2D location." }, "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox": { "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox", "type": "object", "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", "properties": { "left": { "description": "Left X coordinate.", "type": "number", "format": "float" }, "top": { "description": "Top Y coordinate.", "type": "number", "format": "float" }, "bottom": { "description": "Bottom Y coordinate.", "type": "number", "format": "float" }, "right": { "type": "number", "format": "float", "description": "Right X coordinate." } } }, "GoogleCloudVideointelligenceV1p3beta1_WordInfo": { "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", "id": "GoogleCloudVideointelligenceV1p3beta1_WordInfo", "type": "object", "properties": { "startTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string", "format": "google-duration" }, "speakerTag": { "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "type": "integer", "format": "int32", "readOnly": true }, "speakerLabel": { "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.", "type": "string", "readOnly": true }, "endTime": { "type": "string", "format": "google-duration", "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary." }, "confidence": { "readOnly": true, "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "type": "number", "format": "float" }, "word": { "description": "The word corresponding to this set of information.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p1beta1_FaceSegment": { "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment", "description": "Video segment where a face was detected." } }, "id": "GoogleCloudVideointelligenceV1p1beta1_FaceSegment", "type": "object", "description": "Video segment level annotation results for face detection." }, "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative": { "description": "Alternative hypotheses (a.k.a. n-best list).", "id": "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative", "type": "object", "properties": { "transcript": { "type": "string", "description": "Transcript text representing the words that the user spoke." }, "confidence": { "type": "number", "format": "float", "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true }, "words": { "readOnly": true, "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_WordInfo" }, "type": "array" } } }, "GoogleLongrunning_Operation": { "properties": { "response": { "description": "The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.", "type": "object", "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." } }, "done": { "description": "If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.", "type": "boolean" }, "metadata": { "type": "object", "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." }, "description": "Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any." }, "error": { "$ref": "GoogleRpc_Status", "description": "The error result of the operation in case of failure or cancellation." }, "name": { "type": "string", "description": "The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`." } }, "id": "GoogleLongrunning_Operation", "type": "object", "description": "This resource represents a long-running operation that is the result of a network API call." }, "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation": { "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", "id": "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation", "type": "object", "properties": { "frames": { "type": "array", "description": "All video frames where explicit content was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame" } }, "version": { "type": "string", "description": "Feature version." } } }, "GoogleCloudVideointelligenceV1p2beta1_ExportToOutputUriStatus": { "description": "Status of exporting annotation response to user specified `output_uri`.", "id": "GoogleCloudVideointelligenceV1p2beta1_ExportToOutputUriStatus", "type": "object", "properties": { "state": { "type": "string", "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ], "readOnly": true, "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ], "description": "Output only. State of the `output_uri` export." }, "status": { "readOnly": true, "$ref": "GoogleRpc_Status", "description": "Output only. Only set if state is FAILED." } } }, "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation": { "id": "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation", "type": "object", "description": "Annotation corresponding to one detected, tracked and recognized logo class.", "properties": { "entity": { "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.", "$ref": "GoogleCloudVideointelligenceV1_Entity" }, "tracks": { "type": "array", "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1_Track" } }, "segments": { "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", "items": { "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame": { "id": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame", "type": "object", "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.", "properties": { "timeOffset": { "description": "The timestamp of the frame in microseconds.", "type": "string", "format": "google-duration" }, "normalizedBoundingBox": { "description": "The normalized bounding box location of this object track for the frame.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox" } } }, "GoogleCloudVideointelligenceV1_FaceFrame": { "id": "GoogleCloudVideointelligenceV1_FaceFrame", "type": "object", "properties": { "normalizedBoundingBoxes": { "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", "items": { "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox" }, "type": "array" }, "timeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location." } }, "description": "Deprecated. No effect.", "deprecated": true }, "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation": { "properties": { "version": { "description": "Feature version.", "type": "string" }, "celebrityTracks": { "description": "The tracks detected from the input video, including recognized celebrities and other detected faces in the video.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack" }, "type": "array" } }, "description": "Celebrity recognition annotation per video.", "id": "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_Track": { "id": "GoogleCloudVideointelligenceV1beta2_Track", "type": "object", "description": "A track of an object instance.", "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment", "description": "Video segment of a track." }, "confidence": { "type": "number", "format": "float", "description": "Optional. The confidence score of the tracked object." }, "timestampedObjects": { "description": "The object with timestamp and attributes per frame in the track.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_TimestampedObject" }, "type": "array" }, "attributes": { "description": "Optional. Attributes in the track level.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative": { "description": "Alternative hypotheses (a.k.a. n-best list).", "id": "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative", "type": "object", "properties": { "transcript": { "description": "Transcript text representing the words that the user spoke.", "type": "string" }, "confidence": { "type": "number", "format": "float", "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true }, "words": { "readOnly": true, "type": "array", "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_WordInfo" } } } }, "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation": { "description": "Annotations corresponding to one tracked object.", "id": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation", "type": "object", "properties": { "trackId": { "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.", "type": "string", "format": "int64" }, "confidence": { "type": "number", "format": "float", "description": "Object category's labeling confidence of this track." }, "version": { "description": "Feature version.", "type": "string" }, "segment": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment", "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears." }, "entity": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity", "description": "Entity to specify the object category that this track is labeled as." }, "frames": { "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress": { "id": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress", "type": "object", "description": "Annotation progress for a single video.", "properties": { "exportStatus": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExportToOutputUriStatus", "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request." }, "startTime": { "description": "Time when the request was received.", "type": "string", "format": "google-datetime" }, "feature": { "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Person detection." ], "description": "Specifies which feature is being tracked if the request contains more than one feature.", "type": "string", "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "PERSON_DETECTION" ] }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "progressPercent": { "type": "integer", "format": "int32", "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed." }, "updateTime": { "description": "Time of the most recent update.", "type": "string", "format": "google-datetime" }, "segment": { "description": "Specifies which segment is being tracked if the request contains more than one segment.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" } } }, "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation": { "properties": { "entity": { "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.", "$ref": "GoogleCloudVideointelligenceV1beta2_Entity" }, "tracks": { "type": "array", "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_Track" } }, "segments": { "type": "array", "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" } } }, "description": "Annotation corresponding to one detected, tracked and recognized logo class.", "id": "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox": { "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox", "type": "object", "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", "properties": { "right": { "description": "Right X coordinate.", "type": "number", "format": "float" }, "bottom": { "type": "number", "format": "float", "description": "Bottom Y coordinate." }, "left": { "description": "Left X coordinate.", "type": "number", "format": "float" }, "top": { "description": "Top Y coordinate.", "type": "number", "format": "float" } } }, "GoogleRpc_Status": { "properties": { "details": { "type": "array", "description": "A list of messages that carry the error details. There is a common set of message types for APIs to use.", "items": { "type": "object", "additionalProperties": { "description": "Properties of the object. Contains field @type with type URL.", "type": "any" } } }, "code": { "type": "integer", "format": "int32", "description": "The status code, which should be an enum value of google.rpc.Code." }, "message": { "description": "A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.", "type": "string" } }, "id": "GoogleRpc_Status", "type": "object", "description": "The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors)." }, "GoogleCloudVideointelligenceV1_Track": { "description": "A track of an object instance.", "id": "GoogleCloudVideointelligenceV1_Track", "type": "object", "properties": { "segment": { "description": "Video segment of a track.", "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" }, "confidence": { "type": "number", "format": "float", "description": "Optional. The confidence score of the tracked object." }, "timestampedObjects": { "description": "The object with timestamp and attributes per frame in the track.", "items": { "$ref": "GoogleCloudVideointelligenceV1_TimestampedObject" }, "type": "array" }, "attributes": { "description": "Optional. Attributes in the track level.", "items": { "$ref": "GoogleCloudVideointelligenceV1_DetectedAttribute" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation": { "id": "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation", "type": "object", "description": "Annotation corresponding to one detected, tracked and recognized logo class.", "properties": { "segments": { "type": "array", "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" } }, "entity": { "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity" }, "tracks": { "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation": { "properties": { "tracks": { "description": "The face tracks with attributes.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Track" }, "type": "array" }, "thumbnail": { "description": "The thumbnail of a person's face.", "type": "string", "format": "byte" }, "version": { "description": "Feature version.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation", "type": "object", "description": "Face detection annotation." }, "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject": { "properties": { "normalizedBoundingBox": { "description": "Normalized Bounding box in a frame, where the object is located.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox" }, "timeOffset": { "type": "string", "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object." }, "attributes": { "type": "array", "description": "Optional. The attributes of the object in the bounding box.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute" } }, "landmarks": { "type": "array", "description": "Optional. The detected landmarks.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark" } } }, "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.", "id": "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation": { "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment", "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears." }, "entity": { "description": "Entity to specify the object category that this track is labeled as.", "$ref": "GoogleCloudVideointelligenceV1beta2_Entity" }, "frames": { "type": "array", "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame" } }, "version": { "description": "Feature version.", "type": "string" }, "trackId": { "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.", "type": "string", "format": "int64" }, "confidence": { "description": "Object category's labeling confidence of this track.", "type": "number", "format": "float" } }, "description": "Annotations corresponding to one tracked object.", "id": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_Track": { "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", "description": "Video segment of a track." }, "timestampedObjects": { "type": "array", "description": "The object with timestamp and attributes per frame in the track.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject" } }, "attributes": { "type": "array", "description": "Optional. Attributes in the track level.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute" } }, "confidence": { "description": "Optional. The confidence score of the tracked object.", "type": "number", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_Track", "type": "object", "description": "A track of an object instance." }, "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentDetectionConfig": { "properties": { "model": { "description": "Model to use for explicit content detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".", "type": "string" } }, "description": "Config for EXPLICIT_CONTENT_DETECTION.", "id": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentDetectionConfig", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults": { "properties": { "inputUri": { "type": "string", "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)." }, "segment": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment", "description": "Video segment on which the annotation is run." }, "textAnnotations": { "type": "array", "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation" } }, "frameLabelAnnotations": { "description": "Label annotations on frame level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" }, "type": "array" }, "logoRecognitionAnnotations": { "type": "array", "description": "Annotations for list of logos detected, tracked and recognized in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation" } }, "explicitAnnotation": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation", "description": "Explicit content annotation." }, "faceAnnotations": { "description": "Deprecated. Please use `face_detection_annotations` instead.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation" }, "type": "array", "deprecated": true }, "shotLabelAnnotations": { "type": "array", "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" } }, "objectAnnotations": { "description": "Annotations for list of objects detected and tracked in video.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation" }, "type": "array" }, "error": { "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.", "$ref": "GoogleRpc_Status" }, "shotAnnotations": { "description": "Shot annotations. Each shot is represented as a video segment.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "type": "array" }, "speechTranscriptions": { "description": "Speech transcription.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription" }, "type": "array" }, "segmentLabelAnnotations": { "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" }, "type": "array" }, "shotPresenceLabelAnnotations": { "type": "array", "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" } }, "personDetectionAnnotations": { "type": "array", "description": "Person detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation" } }, "faceDetectionAnnotations": { "type": "array", "description": "Face detection annotations.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation" } }, "segmentPresenceLabelAnnotations": { "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" }, "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults", "type": "object", "description": "Annotation results for a single video." }, "GoogleCloudVideointelligenceV1p1beta1_LabelSegment": { "id": "GoogleCloudVideointelligenceV1p1beta1_LabelSegment", "type": "object", "description": "Video segment level annotation results for label detection.", "properties": { "segment": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment", "description": "Video segment where a label was detected." }, "confidence": { "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1beta2_LabelSegment": { "properties": { "segment": { "description": "Video segment where a label was detected.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "confidence": { "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number", "format": "float" } }, "description": "Video segment level annotation results for label detection.", "id": "GoogleCloudVideointelligenceV1beta2_LabelSegment", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_SpeechContext": { "id": "GoogleCloudVideointelligenceV1p3beta1_SpeechContext", "type": "object", "description": "Provides \"hints\" to the speech recognizer to favor specific words and phrases in the results.", "properties": { "phrases": { "description": "Optional. A list of strings containing words and phrases \"hints\" so that the speech recognition is more likely to recognize them. This can be used to improve the accuracy for specific words and phrases, for example, if specific commands are typically spoken by the user. This can also be used to add additional words to the vocabulary of the recognizer. See [usage limits](https://cloud.google.com/speech/limits#content).", "items": { "type": "string" }, "type": "array" } } }, "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation": { "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", "id": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation", "type": "object", "properties": { "frames": { "type": "array", "description": "All video frames where explicit content was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame" } }, "version": { "description": "Feature version.", "type": "string" } } }, "GoogleCloudVideointelligenceV1_AnnotateVideoProgress": { "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "id": "GoogleCloudVideointelligenceV1_AnnotateVideoProgress", "type": "object", "properties": { "annotationProgress": { "type": "array", "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1_VideoAnnotationProgress" } } } }, "GoogleCloudVideointelligenceV1p3beta1_LabelDetectionConfig": { "id": "GoogleCloudVideointelligenceV1p3beta1_LabelDetectionConfig", "type": "object", "description": "Config for LABEL_DETECTION.", "properties": { "model": { "type": "string", "description": "Model to use for label detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\"." }, "stationaryCamera": { "type": "boolean", "description": "Whether the video has been shot from a stationary (i.e., non-moving) camera. When set to true, might improve detection accuracy for moving objects. Should be used with `SHOT_AND_FRAME_MODE` enabled." }, "labelDetectionMode": { "enumDescriptions": [ "Unspecified.", "Detect shot-level labels.", "Detect frame-level labels.", "Detect both shot-level and frame-level labels." ], "description": "What labels should be detected with LABEL_DETECTION, in addition to video-level labels or segment-level labels. If unspecified, defaults to `SHOT_MODE`.", "type": "string", "enum": [ "LABEL_DETECTION_MODE_UNSPECIFIED", "SHOT_MODE", "FRAME_MODE", "SHOT_AND_FRAME_MODE" ] }, "frameConfidenceThreshold": { "description": "The confidence threshold we perform filtering on the labels from frame-level detection. If not set, it is set to 0.4 by default. The valid range for this threshold is [0.1, 0.9]. Any value set outside of this range will be clipped. Note: For best results, follow the default threshold. We will update the default threshold everytime when we release a new model.", "type": "number", "format": "float" }, "videoConfidenceThreshold": { "description": "The confidence threshold we perform filtering on the labels from video-level and shot-level detections. If not set, it's set to 0.3 by default. The valid range for this threshold is [0.1, 0.9]. Any value set outside of this range will be clipped. Note: For best results, follow the default threshold. We will update the default threshold everytime when we release a new model.", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1beta2_AnnotateVideoResponse": { "properties": { "annotationResults": { "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults" }, "type": "array" } }, "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "id": "GoogleCloudVideointelligenceV1beta2_AnnotateVideoResponse", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_DetectedAttribute": { "properties": { "value": { "type": "string", "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc." }, "name": { "type": "string", "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document." }, "confidence": { "description": "Detected attribute confidence. Range [0, 1].", "type": "number", "format": "float" } }, "description": "A generic detected attribute represented by name in string format.", "id": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation": { "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", "id": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation", "type": "object", "properties": { "frames": { "type": "array", "description": "All video frames where explicit content was detected.", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame" } }, "version": { "type": "string", "description": "Feature version." } } }, "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly": { "properties": { "vertices": { "description": "Normalized vertices of the bounding polygon.", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex" }, "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly", "type": "object", "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box." }, "GoogleCloudVideointelligenceV1p3beta1_TextFrame": { "properties": { "rotatedBoundingBox": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly", "description": "Bounding polygon of the detected text for this frame." }, "timeOffset": { "description": "Timestamp of this frame.", "type": "string", "format": "google-duration" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_TextFrame", "type": "object", "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets." }, "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation": { "properties": { "tracks": { "type": "array", "description": "The detected tracks of a person.", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_Track" } }, "version": { "type": "string", "description": "Feature version." } }, "description": "Person detection annotation per video.", "id": "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation", "type": "object" } }, "discoveryVersion": "v1", "revision": "20260428", "baseUrl": "https://videointelligence.googleapis.com/", "mtlsRootUrl": "https://videointelligence.mtls.googleapis.com/", "basePath": "", "kind": "discovery#restDescription", "icons": { "x16": "http://www.google.com/images/icons/product/search-16.gif", "x32": "http://www.google.com/images/icons/product/search-32.gif" }, "ownerName": "Google", "title": "Cloud Video Intelligence API", "auth": { "oauth2": { "scopes": { "https://www.googleapis.com/auth/cloud-platform": { "description": "See, edit, configure, and delete your Google Cloud data and see the email address for your Google Account." } } } }, "description": "Detects objects, explicit content, and scene changes in videos. It also specifies the region for annotation and transcribes speech to text. Supports both asynchronous API and streaming API.", "servicePath": "", "id": "videointelligence:v1p3beta1" }